A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method for compression includes receiving a first image and a first scheme as inputs for an autoencoder network; determining a first Lagrange multiplier based on the first scheme; and using the first image and the first Lagrange multiplier as inputs, computing a second image from the autoencoder network. The autoencoder network is trained using a plurality of Lagrange multipliers and a second image as training inputs.

Methods and devices for coding point clouds using direct coding mode to code coordinates of a point within a sub-volume associated with a current node instead of a pattern of occupancy for child nodes. Eligibility for use of direct coding is based on occupancy data from another node. If eligible, then a flag is represented in the bitstream to signal whether direct coding is applied to points in the sub-volume or not.

Methods and devices for coding point clouds using direct coding mode to code coordinates of a point within a sub-volume associated with a current node instead of a pattern of occupancy for child nodes. Eligibility for use of direct coding is based on occupancy data from another node. If eligible, then a flag is represented in the bitstream to signal whether direct coding is applied to points in the sub-volume or not.

Techniques described herein relate to systems and methods of data storage, and more particularly to providing layering of file system functionality on an object interface. In certain embodiments, file system functionality may be layered on cloud object interfaces to provide cloud-based storage while allowing for functionality expected from a legacy applications. For instance, POSIX interfaces and semantics may be layered on cloud-based storage, while providing access to data in a manner consistent with file-based access with data organization in name hierarchies. Various embodiments also may provide for memory mapping of data so that memory map changes are reflected in persistent storage while ensuring consistency between memory map changes and writes. For example, by transforming a ZFS file system disk-based storage into ZFS cloud-based storage, the ZFS file system gains the elastic nature of cloud storage.

A data compressor a zero-value remover, a zero bit mask generator, a non-zero values packer, and a row-pointer generator. The zero-value remover receives 2.sup.N bit streams of values and outputs 2.sup.N non-zero-value bit streams having zero values removed from each respective bit stream. The zero bit mask generator receives the 2.sup.N bit streams of values and generates a zero bit mask for a predetermined number of values of each bit stream in which each zero bit mask indicates a location of a zero value in the predetermined number of values corresponding to the zero bit mask. The non-zero values packer receives the 2.sup.N non-zero-value bit streams and forms a group of packed non-zero values. The row-pointer generator that generates a row-pointer for each group of packed non-zero values.

A data compressor a zero-value remover, a zero bit mask generator, a non-zero values packer, and a row-pointer generator. The zero-value remover receives 2.sup.N bit streams of values and outputs 2.sup.N non-zero-value bit streams having zero values removed from each respective bit stream. The zero bit mask generator receives the 2.sup.N bit streams of values and generates a zero bit mask for a predetermined number of values of each bit stream in which each zero bit mask indicates a location of a zero value in the predetermined number of values corresponding to the zero bit mask. The non-zero values packer receives the 2.sup.N non-zero-value bit streams and forms a group of packed non-zero values. The row-pointer generator that generates a row-pointer for each group of packed non-zero values.

A device configured to compress a tensor including a plurality of cells includes: a quadtree generator configured to generate a quadtree searching for a non-zero cell included in the tensor and extract at least one parameter value from the quadtree; a mode selector configured to determine a compression mode based on the at least one parameter; and a bitstream generator configured to generate a bitstream by compressing the tensor based on the compression mode.

Disclosed is a processor chip that includes on-chip and off-chip software. The chip is optimized for hyperdimensional, fixed-point vector algebra to efficiently store, process, and retrieve information. A specialized on-chip data-embedding algorithm uses algebraic logic gates to convert off-chip normal data, such as images and spreadsheets, into discrete, abstract vector space where information is processed with off-chip software and on-chip accelerated computation via a desaturation method. Information is retrieved using an on-chip optimized decoding algorithm. Additional software provides an interface between a CPU and the processor chip to manage information processing instructions for efficient data transfer on- and off-chip in addition to providing intelligent processing that associates input information to allow for suggestive outputs.

Disclosed is a processor chip that includes on-chip and off-chip software. The chip is optimized for hyperdimensional, fixed-point vector algebra to efficiently store, process, and retrieve information. A specialized on-chip data-embedding algorithm uses algebraic logic gates to convert off-chip normal data, such as images and spreadsheets, into discrete, abstract vector space where information is processed with off-chip software and on-chip accelerated computation via a desaturation method. Information is retrieved using an on-chip optimized decoding algorithm. Additional software provides an interface between a CPU and the processor chip to manage information processing instructions for efficient data transfer on- and off-chip in addition to providing intelligent processing that associates input information to allow for suggestive outputs.

A method is disclosed to reduce computation in a self-attention deep-learning model. A feature-map regularization term is added to a loss function while training the self-attention model. At least one low-magnitude feature is removed from at least one feature map of the self-attention model during inference. Weights of the self-attention model are quantized after the self-attention model has been trained. Adding the feature-map regularization term reduces activation values of feature maps, and removing the at least one low-magnitude feature from at least one feature map may be performed by setting the low-magnitude feature to be equal to zero based on the low-magnitude feature having a value that is less than a predetermined threshold. Feature maps of the self-attention model quantized and compressed.